Presentation | 2006/12/14 Selection of Prediction Sentence Candidates Based on Phoneme Recognition in Spoken Dialogue System Hiromasa TERASHI, Masafumi NISHIDA, Yasuo HORIUCHI, Akira ICHIKAWA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We aim to construct a spoken dialogue system for multiple in-vehicle information system. It is necessary to recognize a domain and utterance correctly from the viewpoint of safety and immediateness under driving condition. We have proposed a method that predicts user's utterances by recognizing prediction sentences of each dialogue state based on discourse tags. However, it is difficult to recognize the domain and utterance in the spoken dialogue of multi-domain because there are a lot of dialogue states and prediction sentences. In this study, we propose a method using the prediction sentence and phoneme recognition. The method performs the phoneme recognition and compares the recognition result with the prediction sentence in all domain by DP matching and recognizes for prediction sentence candidates obtained by DP matching. We conducted experiments in multiple in-vehicle information system. As a result, recognition accuracy was 87.9% for prediction sentences in all domain and was 96.3% by the proposed method. Therefore, the proposed method was effective in the spoken dialogue of multi-domain. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Multi-domain / In-vehicle information system / Spoken dialogue / Phoneme recognition / Prediction sentence recognition / DP matching |
Paper # | NLC2006-46,SP2006-102 |
Date of Issue |
Conference Information | |
Committee | NLC |
---|---|
Conference Date | 2006/12/14(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Natural Language Understanding and Models of Communication (NLC) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Selection of Prediction Sentence Candidates Based on Phoneme Recognition in Spoken Dialogue System |
Sub Title (in English) | |
Keyword(1) | Multi-domain |
Keyword(2) | In-vehicle information system |
Keyword(3) | Spoken dialogue |
Keyword(4) | Phoneme recognition |
Keyword(5) | Prediction sentence recognition |
Keyword(6) | DP matching |
1st Author's Name | Hiromasa TERASHI |
1st Author's Affiliation | Graduate School of Science and Technology, Chiba University() |
2nd Author's Name | Masafumi NISHIDA |
2nd Author's Affiliation | Graduate School of Science and Technology, Chiba University |
3rd Author's Name | Yasuo HORIUCHI |
3rd Author's Affiliation | Graduate School of Science and Technology, Chiba University |
4th Author's Name | Akira ICHIKAWA |
4th Author's Affiliation | Graduate School of Science and Technology, Chiba University |
Date | 2006/12/14 |
Paper # | NLC2006-46,SP2006-102 |
Volume (vol) | vol.106 |
Number (no) | 441 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |